If you want to build your own workflows around Kyron — whether that's publishing lessons automatically, or letting your team manage content through Claude or ChatGPT — you have two options: our public API and MCP (Model Context Protocol). This guide explains what each one is, when to use which, and how to set them up.
Why this matters
Picking the right connection method up front saves you time and avoids rework. The API and MCP are built for different kinds of users and different kinds of tasks, so choosing the one that matches your team's technical setup and goals will get you up and running faster.
API vs. MCP at a glance
| API | MCP |
Best for | Developers building custom integrations | Teams using Claude or ChatGPT |
Technical skill needed | Requires writing and deploying code | No coding required |
What you can do | Primarily creating and publishing lessons | Anything available in Studio |
Typical user | Engineering/dev team | Instructors and curriculum developers |
When to use the API
The API is the right choice when:
You're building an internal app that integrates with several third-party tools, including Kyron
Your main goal is creating and publishing lessons
Note: If you need to edit lessons or do something beyond creating/publishing, the API may not support it yet. Reach out to us so we can discuss feasibility with our engineering team.
When to use MCP
MCP is the right choice when:
Your workflow is already built around Claude or ChatGPT
You need broad access to Kyron — essentially, anything you could do manually in Studio
The person setting this up isn't comfortable writing or deploying code
Setting up API access
Full documentation, including endpoints and authentication details, is available at: https://www.kyronlearning.com/api-docs
Setting up MCP access
Claude
These steps are for a Claude organization owner — typically someone on your institution's IT team.
Go to your organization's connector list: https://claude.ai/admin-settings/connectors
Click Add > Custom > Web
Name the connector "Kyron Learning"
Set the URL to https://www.kyronlearning.com/mcp
Click Continue and finish creating the connector using the default settings
Kyron supports OAuth Client ID Metadata Documents (CIMD), so no manual client setup is needed
Once connected, your connector details should look like this:
To allow workflows that involve uploading files (e.g. creating lessons aligned to existing content or uploading specific, pre-existing images to lessons), you’ll also need to authorize an additional domain.
Under “Additional allowed domains”, add “storage.googleapis.com”
Click “Add”
ChatGPT
Click “+” in the top right corner
Name the tool “Kyron Learning”
Set connection to “https://www.kyronlearning.com/mcp”
Click “Create”
Questions about which option fits your use case? Reach out to our team and we'll help you figure out the best path.